goal-engineer

Featured

Use when the user wants to AUTHOR an unattended dispatch for either: (1) a goal-driven evaluator-optimizer loop of the GENERATE-AND-SELECT kind (generate candidates → grade against a rubric → iterate by reason-code → keep the best; the human picks the final selection), or (2) a lean build-to-spec run whose build spec is ALREADY FROZEN (approved ADR / locked design / accepted machine-checkable AC) and the only missing piece is the unattended-execution wrapper. A fresh-session agent runs the dispatch hands-off while the human only watches traffic-light push notifications. Interview-style forcing questions lock the spec, then it emits a self-contained dispatch markdown + a channel-agnostic notification protocol. This is the upstream SPEC AUTHOR, NOT a runtime: the dispatch is run by Claude Code's /goal, a headless `-p` session, or any unattended agent — /goal is the engine, this writes what you feed it. It NEVER authors build specs, product decisions, or AC — creating a build spec / PRD from raw input is prd-cre

AI & Automation 76 stars 13 forks Updated 6 days ago MIT

Install

View on GitHub

Quality Score: 92/100

Stars 20%

Recency 20%

100

Frontmatter 20%

Documentation 15%

100

Issue Health 10%

License 10%

100

Description 5%

100

Skill Content

# /goal-engineer — Unattended Goal-Loop Dispatch Architect You are a **goal-loop dispatch architect** — the *upstream spec author*, not the runtime. You turn a vague "I want an agent to grind on X by itself" into a **self-contained dispatch markdown** that a *fresh-session* agent can execute hands-off — generating candidates, grading them against a rubric, iterating by reason-code, keeping the best — while the human only monitors traffic-light (🟢🟡🔴) push notifications and makes the taste calls (the **final selection**) at gates. This skill **produces a spec + a notification protocol. It does NOT run the loop itself.** ## What this is / isn't（先讀,避免叫錯工具） | | `goal-engineer`（本 skill）| 不是這個 | |---|---|---| | 層 | **規格作者**(寫 dispatch) | **引擎**(跑迴圈)= Claude Code `/goal` | | 模式 | goal-driven evaluator-optimizer,**generate-and-select**(產候選→評→挑) | time-driven 週期重跑(`/loop`、cron) | | 內容型 | 抽卡 / bug-hunt / 候選擇優;**窄例外**:規格已凍結的 lean build dispatch(已核可 ADR / 鎖定設計 → 只包無人值守執行規格,見 Frozen Spec Check) | 從 raw input 產 build spec / PRD / 補產品決策 = `prd-create` | | 產出 | 一份 dispatch markdown + 通知協定 | 註冊定時推播(`skill-cron`) | | 誰來跑 | **新 session 無人值守 agent**(可拿 `/goal` / headless `-p` 當引擎) | 當前 session | | 人的角色 | 看 🟢🟡🔴、在 gate 挑最終選定 | 全程盯著 | **CRITICAL — 這不是 `/goal`**:Claude Code 內建的 `/goal` 是**引擎**(給一個可判真假的條件,獨立小模型每輪判��標、沒過再跑一輪、達標自停)。本 skill 是**上游**:把你要交給 `/goal`(或 headless `-p` session)跑的那個 goal,連同**兩層閘 / 原因碼 / 對抗審查 / 通知協定 / 可重現紀律**一起工程化。`/goal` 的判官只是一個 yes/no、對「這張圖有沒有到位 / 這個 bug 是不是真的」這種主觀又要...

Details

Author: KerberosClaw
Repository: KerberosClaw/kc_ai_skills
Created: 4 months ago
Last Updated: 6 days ago
Language: Python
License: MIT

Integrates with

Anthropic · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

goal

Goal Prompt design coach. Turns vague tasks into precise goal prompts that fit the five-element framework (outcome / verification / constraint / iteration policy / error handling) plus an optional rubric — so Claude Code's /goal, OpenAI Codex's /goal, or Manus Agent's /goal has a clear target to iterate against. 把模糊任務透過反問轉成五元素 + rubric 的精確 goal prompt。Outbound routing — a full software product (multiple features, deployed, used by others) → defer to idea-to-spec if installed; a finished spec to decompose into a dependency-ordered goal graph → defer to goal-decomposer if installed. 完整軟體產品讓位給 idea-to-spec、整份規格拆成依賴圖讓位給 goal-decomposer（皆以已安裝為前提，未安裝則繼續但須提醒用戶範圍差異）。

1 Updated 2 days ago

dragon375014

AI & Automation Listed

goal-skill

Load when the user wants to drive a non-trivial goal to completion under rigorous sub-agent orchestration, or invokes `/goal-skill`. Triggers: "drive this goal to completion", "subagent-driven development", "SDD", "orchestrate this build", "run this end-to-end with reviewers", "build this properly with planning and validation", or setting a substantial multi-step feature/fix that warrants planned-then-reviewed-then-implemented-then-validated execution. Use for work too large or risky for a single straight-line pass.

10 Updated today

meanllbrl

AI & Automation Listed

goal-charter

写 goal 章程——把一段本来要靠人逐工序把关的施工，压成一份"目标+验证器+边界+自愈清单"的执行契约，交给 goal 模式自主跑到底，人只在拍板章程和终点验收各出面一次。用于标准研发流程第 6 步（规格冻结之后、施工之前），也用于任何"我要它一口气跑完、别每隔十分钟问我一次"的长程自主执行。触发场景：写 goal 章程、给 goal/agent 定目标与边界、把施工+提交+部署+测试+执行记录打成一个自主闭环、给已跑偏的 goal 重定边界、**章程写完后怎么真正启动 `/goal`（完成条件怎么写、evaluator 判得到什么、限轮与 auto mode）**。本 skill 管章程怎么写（写什么、写多长、边界怎么定义才防得住）与章程→`/goal` 的交接（§13）；不管设计怎么做（`lightweight-design`）、用例怎么写（`test-case-design`）、总控子任务怎么编排（`task-control-doc`）。

3 Updated today

BackToCimaCoppi